← all papers · overview

Goal-guided Generative Prompt Injection Attack On Large Language Models

Abstract

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface, thus causing LLMs model security challenges. Although there is currently a large amount of research on prompt injection attacks, most of these black-box attacks use heuristic str

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).